About the job
Join Our Team as an Embedded AI Engineer at Applied Intuition!
As an in-office company, we expect our employees to work from the Applied Intuition office five days a week. However, we value flexibility and trust our employees to manage their schedules responsibly. This might include occasional remote work, starting the day with morning meetings from home, or leaving early to accommodate family commitments.
About the Role
We are developing cutting-edge on-device intelligence for a next-generation Android Automotive platform. In this role, you will oversee the complete lifecycle of embedded machine learning systems, ensuring that models operate reliably and safely in production environments while managing real-world constraints such as latency, thermal limits, and functional safety.
Your Responsibilities
Deploy and manage production-quality ML inference and learning systems on Android Automotive (AAOS).
Implement on-device multimodal large language models (LLMs), including schema design and safe integration with local vehicle APIs.
Integrate models using frameworks like TensorFlow Lite, ONNX Runtime, or specialized vendor SDKs.
Profile and optimize models to meet strict requirements for latency, memory usage, power consumption, and thermal management.
